EUVIMEDEUVIMED entdecken
Crossref

Multimodal Artificial Intelligence Model From Baseline Histopathology Adds Prognostic Information for Distant Recurrence Assessment in Hormone Receptor–Positive/Human Epidermal Growth Factor Receptor 2–Negative Early Breast Cancer

Daniel Kates-Harbeck iD, Hans Kreipe, Oleg Gluz iD, Matthias Christgen iD, Sherko Kuemmel iD, Monika Graeser iD, Ulrike Nitz, Sven Mahner, Doris Mayr, Rachel Wuerstlein, Akinori Mitani, Jingbin Zhang und 10 weitere

JCO Clinical Cancer Informatics · 2025

DOI: 10.1200/cci-24-00287 ↗

Kurz gefasst

Fachartikel in der Zeitschrift JCO Clinical Cancer Informatics, 2025. Verfasst von Daniel Kates-Harbeck und 21 weiteren Autor:innen. Beteiligte Einrichtung: Department of Obstetrics and Gynecology, Breast Center and CCC Munich, LMU University Hospital, Munich, Germany. Hauptthemen laut MEDLINE: Breast Neoplasms, Erb-b2 Receptor Tyrosine Kinases, Artificial Intelligence, Neoplasm Recurrence, Local. Die Arbeit nennt 32 Literaturangaben.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

PURPOSE Prognostic assessment in hormone receptor–positive (HR+)/human epidermal growth factor receptor 2–negative (HER2–) early breast cancer (EBC) remains challenging, given relatively low rates of disease progression. Modern artificial intelligence (AI)–based techniques have provided advanced prognostic tools in cancer. PATIENTS AND METHODS The Artera multimodal AI (MMAI) platform, using digital histopathology and clinical data, was applied to develop and test a prognostic risk assessment algorithm in HR+/HER2– EBC. Hematoxylin and eosin (H&E) slides from pretreatment breast biopsy and surgical specimens were digitized from the WSG PlanB and ADAPT trials. Patients with available images and complete data (n = 5,259) were stratified by trial, treatment, and distant metastasis (DM) into training (development: 60%) and internal validation (holdout: 40%) cohorts. The algorithm provided prognostic DM risk scores on the basis of image data and clinical variables (age, T and N stages, and tumor size). Univariable and multivariable Fine-Gray models were used to assess performance on the test cohort; subdistribution hazard ratios (sHR) are reported per standard deviation increase of the model scores. Prespecified prognostic subgroups for analysis were defined by nodal status, menopausal status, and tumor grade. RESULTS The trained MMAI score was significantly associated with risk of DM in the test cohort (sHR, 2.3 [95% CI, 2.0 to 2.8]) as a whole and across subgroups. The score remained significant (sHR, 2.2 [95% CI, 1.7 to 2.8]) after adjusting for clinical prognostic factors. The MMAI image component alone had significant prognostic value (sHR, 1.6 [95% CI, 1.3 to 1.9]) in the test cohort; it also had significant prognostic value separately within the G2 and G3 subgroups, with sHR of 1.5 per standard deviation increase, and in most of the other predefined clinical subgroups. CONCLUSION MMAI using digital pathology from H&E slides provides enhanced prognostic quality in HR+/HER2– EBC and could help to advance personalized breast cancer management.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Breast NeoplasmsErb-b2 Receptor Tyrosine KinasesArtificial IntelligenceNeoplasm Recurrence, LocalHumansFemalePrognosisMiddle AgedReceptors, EstrogenReceptors, ProgesteroneAdultAgedAlgorithmsRisk AssessmentBiomarkers, Tumor

Substanzen

Erb-b2 Receptor Tyrosine KinasesReceptors, EstrogenReceptors, ProgesteroneBiomarkers, TumorERBB2 protein, human

Autor:innen und Institutionen

  • Department of Obstetrics and Gynecology, Breast Center and CCC Munich, LMU University Hospital, Munich, Germany.
  • Westdeutsche Studiengruppe, Mönchengladbach, Germany.
  • University of Leipzig, Leipzig, Germany.
  • Institute for Pathology, MHH, Hannover, Germany.
  • Breast Center Niederrhein, Johanniter-Kliniken Evang. Bethesda Hospital, Oberhausen, Germany.
  • Kliniken Essen-Mitte, Essen, Germany.

ORCID-Profile: Daniel Kates-Harbeck, Oleg Gluz, Matthias Christgen, Sherko Kuemmel, Monika Graeser, Hans Pinckaers, Nancy Lin, Nadia Harbeck

Zitieren

APA

Kates-Harbeck, D., Kreipe, H., Gluz, O., Christgen, M., Kuemmel, S., Graeser, M., Nitz, U., Mahner, S., Mayr, D., Wuerstlein, R., Mitani, A., Zhang, J., Pinckaers, H., Smit, G., Ren, Y., Joun, S., Griffin, J., Lin, N., Feng, F., …, & Harbeck, N. (2025). Multimodal Artificial Intelligence Model From Baseline Histopathology Adds Prognostic Information for Distant Recurrence Assessment in Hormone Receptor–Positive/Human Epidermal Growth Factor Receptor 2–Negative Early Breast Cancer. JCO Clinical Cancer Informatics. https://doi.org/10.1200/cci-24-00287

Vancouver

Kates-Harbeck D, Kreipe H, Gluz O, Christgen M, Kuemmel S, Graeser M, et al. Multimodal Artificial Intelligence Model From Baseline Histopathology Adds Prognostic Information for Distant Recurrence Assessment in Hormone Receptor–Positive/Human Epidermal Growth Factor Receptor 2–Negative Early Breast Cancer. JCO Clinical Cancer Informatics. 2025. doi:10.1200/cci-24-00287

BibTeX
@article{KatesHarbeck2025,
  author = {Kates-Harbeck, Daniel and Kreipe, Hans and Gluz, Oleg and Christgen, Matthias and Kuemmel, Sherko and Graeser, Monika and Nitz, Ulrike and Mahner, Sven and Mayr, Doris and Wuerstlein, Rachel and Mitani, Akinori and Zhang, Jingbin and Pinckaers, Hans and Smit, Gijs and Ren, Yi and Joun, Songwan and Griffin, Jacqueline and Lin, Nancy and Feng, Felix and Esteva, Andre and Kates, Ronald and Harbeck, Nadia},
  title = {Multimodal Artificial Intelligence Model From Baseline Histopathology Adds Prognostic Information for Distant Recurrence Assessment in Hormone Receptor–Positive/Human Epidermal Growth Factor Receptor 2–Negative Early Breast Cancer},
  journal = {JCO Clinical Cancer Informatics},
  year = {2025},
  doi = {10.1200/cci-24-00287}
}
Kostenlos starten →